Cadences#
Show imports
import os
from collections import defaultdict, Counter
from git import Repo
import dimcat as dc
import ms3
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from utils import STD_LAYOUT, CADENCE_COLORS, color_background, value_count_df, get_repo_name, print_heading, resolve_dir
Show source
CORPUS_PATH = os.path.abspath(os.path.join('..', '..'))
print_heading("Notebook settings")
print(f"CORPUS_PATH: {CORPUS_PATH!r}")
CORPUS_PATH = resolve_dir(CORPUS_PATH)
Notebook settings
-----------------
CORPUS_PATH: '/home/runner/work/workflow_deployment/romantic_piano_corpus'
Show source
repo = Repo(CORPUS_PATH)
print_heading("Data and software versions")
print(f"Data repo '{get_repo_name(repo)}' @ {repo.commit().hexsha[:7]}")
print(f"dimcat version {dc.__version__}")
print(f"ms3 version {ms3.__version__}")
Data and software versions
--------------------------
Data repo 'romantic_piano_corpus' @ 0a9eadd
dimcat version 0.3.0
ms3 version 2.2.1
dataset = dc.Dataset()
dataset.load(directory=CORPUS_PATH, parse_tsv=False)
[annotated|all|default]
All corpora
-----------
View: This view is called 'annotated'. It
- excludes pieces that are not contained in the metadata,
- filters out file extensions requiring conversion (such as .xml),
- excludes review files and folders, and
- includes only facets containing 'expanded'.
has active expanded
metadata view detected parsed
corpus
beethoven_piano_sonatas yes annotated 64 64
chopin_mazurkas yes annotated 55 55
debussy_suite_bergamasque yes annotated 4 4
dvorak_silhouettes yes annotated 12 12
grieg_lyric_pieces yes annotated 66 66
liszt_pelerinage yes annotated 19 19
medtner_tales yes annotated 19 19
schumann_kinderszenen yes annotated 13 13
tchaikovsky_seasons yes annotated 12 12
11/12 facets are excluded from this view.
There are 1 orphans that could not be attributed to any of the respective corpus's pieces.
N = 264 annotated pieces, 264 parsed dataframes.
Metadata#
all_metadata = dataset.data.metadata()
assert len(all_metadata) > 0, "No pieces selected for analysis."
print(f"Concatenated 'metadata.tsv' files cover {len(all_metadata)} of the {dataset.data.count_pieces()} scores.")
all_metadata.reset_index(level=1).groupby(level=0).nth(0).iloc[:,:20]
Concatenated 'metadata.tsv' files cover 264 of the 264 scores.
| piece | TimeSig | KeySig | last_mc | last_mn | length_qb | last_mc_unfolded | last_mn_unfolded | length_qb_unfolded | volta_mcs | all_notes_qb | n_onsets | n_onset_positions | guitar_chord_count | form_label_count | label_count | annotated_key | harmony_version | annotators | reviewers | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| corpus | ||||||||||||||||||||
| beethoven_piano_sonatas | 01-1 | 1: 2/2 | 1: -4 | 154 | 152 | 608.0 | 308.0 | 304.0 | 1216.0 | 1476.00 | 1679 | 985 | 0 | 0 | 241 | f | 2.3.0 | Lars & Ya-Chuan (2.2.0), John Heilig (2.3.0) | AN | |
| chopin_mazurkas | BI105-2op30-2 | 1: 3/4 | 1: 2 | 65 | 64 | 193.0 | 65.0 | 64.0 | 193.0 | 711.00 | 810 | 274 | 0 | 0 | 116 | b | 2.3.0 | Wendelin Bitzan (1.0.0), Adrian Nagel (2.2.0),... | JH, AN, DK | |
| debussy_suite_bergamasque | l075-01_suite_prelude | 1: 4/4 | 1: -1 | 89 | 89 | 356.0 | 89.0 | 89.0 | 356.0 | 1533.67 | 1721 | 870 | 0 | 0 | 274 | F | 2.3.0 | Adrian Nagel (2.1.1), Amelia Brey (2.3.0) | AB, AN | |
| dvorak_silhouettes | op08n01 | 1: 6/8 | 1: 4, 7: -5, 49: 4 | 54 | 52 | 156.5 | 54.0 | 52.0 | 156.5 | 658.75 | 957 | 288 | 0 | 0 | 80 | c# | 2.3.0 | Daniel Grote (2.1.1), Hanné Becker (2.3.0) | Johannes Hentschel (2.1.1), AN | |
| grieg_lyric_pieces | op12n01 | 1: 2/4 | 1: -3 | 23 | 23 | 46.0 | 23.0 | 23.0 | 46.0 | 135.50 | 268 | 156 | 0 | 0 | 43 | Eb | 2.3.0 | Adrian Nagel (2.1.1), John Heilig (2.30) | Adrian Nagel | |
| liszt_pelerinage | 160.01_Chapelle_de_Guillaume_Tell | 1: 4/4 | 1: 0 | 97 | 97 | 388.0 | 97.0 | 97.0 | 388.0 | 1902.42 | 2879 | 1069 | 0 | 0 | 174 | C | 2.3.0 | Adrian Nagel (2.1.1), Amelia Brey (2.3.0) | Johannes Hentschel (1-33 & 82-97), AB, AN | |
| medtner_tales | op08n01 | 1: 4/8 | 1: -3 | 81 | 81 | 162.0 | 81.0 | 81.0 | 162.0 | 603.00 | 1481 | 528 | 0 | 0 | 213 | c | 2.3.0 | Wendelin Bitzan (2.2.0), John Heilig (2.3.0) | Adrian Nagel, DK | |
| schumann_kinderszenen | n01 | 1: 2/4 | 1: 1 | 22 | 22 | 44.0 | 44.0 | 44.0 | 88.0 | 134.33 | 241 | 141 | 0 | 0 | 44 | G | 2.3.0 | Tal Soker (2.1.1), John Heilig (2.3.0) | AN, JHei, JH | |
| tchaikovsky_seasons | op37a01 | 1: 3/4 | 1: 3, 29: 1, 63: 3 | 103 | 103 | 309.0 | 103.0 | 103.0 | 309.0 | 1058.17 | 1537 | 829 | 0 | 0 | 313 | A | 2.3.0 | Adrian Nagel (2.1.1), John Heilig (2.3.0) | Johannes Hentschel, AN |
All annotation labels from the selected pieces#
all_labels = dataset.data.get_facet('expanded')
print(f"{len(all_labels.index)} hand-annotated harmony labels:")
all_labels.iloc[:20].style.apply(color_background, subset="chord")
57455 hand-annotated harmony labels:
| mc | mn | quarterbeats | quarterbeats_all_endings | duration_qb | mc_onset | mn_onset | timesig | staff | voice | label | alt_label | globalkey | localkey | pedal | chord | special | numeral | form | figbass | changes | relativeroot | cadence | phraseend | chord_type | globalkey_is_minor | localkey_is_minor | chord_tones | added_tones | root | bass_note | volta | pedalend | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| corpus | piece | i | |||||||||||||||||||||||||||||||||
| beethoven_piano_sonatas | 01-1 | 0 | 1 | 0 | 0 | 0 | 9.000000 | 0 | 3/4 | 2/2 | 2 | 1 | f.i{ | nan | f | i | nan | i | nan | i | nan | nan | nan | nan | nan | { | m | True | True | (0, -3, 1) | () | 0 | 0 | nan | |
| 1 | 4 | 3 | 9 | 9 | 8.000000 | 0 | 0 | 2/2 | 2 | 1 | V65 | nan | f | i | nan | V65 | nan | V | nan | 65 | nan | nan | nan | nan | Mm7 | True | True | (5, 2, -1, 1) | () | 1 | 5 | nan | |||
| 2 | 6 | 5 | 17 | 17 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | i | nan | f | i | nan | i | nan | i | nan | nan | nan | nan | nan | nan | m | True | True | (0, -3, 1) | () | 0 | 0 | nan | |||
| 3 | 7 | 6 | 21 | 21 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | #viio6 | nan | f | i | nan | #viio6 | nan | #vii | o | 6 | nan | nan | nan | nan | o | True | True | (2, -1, 5) | () | 5 | 2 | nan | |||
| 4 | 8 | 7 | 25 | 25 | 2.000000 | 0 | 0 | 2/2 | 2 | 1 | i6 | nan | f | i | nan | i6 | nan | i | nan | 6 | nan | nan | nan | nan | m | True | True | (-3, 1, 0) | () | 0 | -3 | nan | |||
| 5 | 8 | 7 | 27 | 27 | 2.000000 | 1/2 | 1/2 | 2/2 | 2 | 1 | iio6 | nan | f | i | nan | iio6 | nan | ii | o | 6 | nan | nan | nan | nan | o | True | True | (-1, -4, 2) | () | 2 | -1 | nan | |||
| 6 | 9 | 8 | 29 | 29 | 1.000000 | 0 | 0 | 2/2 | 2 | 1 | V(4)} | nan | f | i | nan | V(4) | nan | V | nan | nan | 4 | nan | nan | } | M | True | True | (1, 0, 2) | () | 1 | 1 | nan | |||
| 7 | 9 | 8 | 30 | 30 | 2.000000 | 1/4 | 1/4 | 2/2 | 2 | 1 | V|HC | nan | f | i | nan | V | nan | V | nan | nan | nan | nan | HC | nan | M | True | True | (1, 5, 2) | () | 1 | 1 | nan | |||
| 8 | 9 | 8 | 32 | 32 | 9.000000 | 3/4 | 3/4 | 2/2 | 2 | 1 | v{ | nan | f | i | nan | v | nan | v | nan | nan | nan | nan | nan | { | m | True | True | (1, -2, 2) | () | 1 | 1 | nan | |||
| 9 | 12 | 11 | 41 | 41 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | III.IVM2 | ii7(2) | f | III | nan | IVM2 | nan | IV | M | 2 | nan | nan | nan | nan | MM7 | True | False | (4, -1, 3, 0) | () | -1 | 4 | nan | |||
| 10 | 13 | 12 | 45 | 45 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | ii7 | nan | f | III | nan | ii7 | nan | ii | nan | 7 | nan | nan | nan | nan | mm7 | True | False | (2, -1, 3, 0) | () | 2 | 2 | nan | |||
| 11 | 14 | 13 | 49 | 49 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | V43 | nan | f | III | nan | V43 | nan | V | nan | 43 | nan | nan | nan | nan | Mm7 | True | False | (2, -1, 1, 5) | () | 1 | 2 | nan | |||
| 12 | 15 | 14 | 53 | 53 | 4.000000 | 0 | 0 | 2/2 | 2 | 1 | I | nan | f | III | nan | I | nan | I | nan | nan | nan | nan | nan | nan | M | True | False | (0, 4, 1) | () | 0 | 0 | nan | |||
| 13 | 16 | 15 | 57 | 57 | 1.000000 | 0 | 0 | 2/2 | 2 | 1 | ii6(2) | nan | f | III | nan | ii6(2) | nan | ii | nan | 6 | 2 | nan | nan | nan | m | True | False | (-1, 3, 4) | () | 2 | -1 | nan | |||
| 14 | 16 | 15 | 58 | 58 | 1.000000 | 1/4 | 1/4 | 2/2 | 2 | 1 | ii6 | nan | f | III | nan | ii6 | nan | ii | nan | 6 | nan | nan | nan | nan | m | True | False | (-1, 3, 2) | () | 2 | -1 | nan | |||
| 15 | 16 | 15 | 59 | 59 | 2.000000 | 1/2 | 1/2 | 2/2 | 2 | 1 | V65/V | nan | f | III | nan | V65/V | nan | V | nan | 65 | nan | V | nan | nan | Mm7 | True | False | (6, 3, 0, 2) | () | 2 | 6 | nan | |||
| 16 | 17 | 16 | 61 | 61 | 3.000000 | 0 | 0 | 2/2 | 2 | 1 | V|HC} | nan | f | III | nan | V | nan | V | nan | nan | nan | nan | HC | } | M | True | False | (1, 5, 2) | () | 1 | 1 | nan | |||
| 17 | 17 | 16 | 64 | 64 | 1.000000 | 3/4 | 3/4 | 2/2 | 2 | 1 | I6{ | nan | f | III | nan | I6 | nan | I | nan | 6 | nan | nan | nan | { | M | True | False | (4, 1, 0) | () | 0 | 4 | nan | |||
| 18 | 18 | 17 | 65 | 65 | 1.000000 | 0 | 0 | 2/2 | 2 | 1 | ii6(2) | nan | f | III | nan | ii6(2) | nan | ii | nan | 6 | 2 | nan | nan | nan | m | True | False | (-1, 3, 4) | () | 2 | -1 | nan | |||
| 19 | 18 | 17 | 66 | 66 | 1.000000 | 1/4 | 1/4 | 2/2 | 2 | 1 | ii6 | nan | f | III | nan | ii6 | nan | ii | nan | 6 | nan | nan | nan | nan | m | True | False | (-1, 3, 2) | () | 2 | -1 | nan |
Filtering out pieces without cadence annotations#
hascadence = dc.HasCadenceAnnotationsFilter().process_data(dataset)
assert () in hascadence.indices and len(hascadence.indices[()]) > 0, "No cadences found."
print(f"Before: {len(dataset.indices[()])} pieces; after removing those without cadence labels: {len(hascadence.indices[()])}")
Before: 264 pieces; after removing those without cadence labels: 258
Show corpora containing pieces with cadence annotations#
grouped_by_corpus = dc.CorpusGrouper().process_data(hascadence)
corpora = {group[0]: f"{len(ixs)} pieces" for group, ixs in grouped_by_corpus.indices.items()}
print(f"{len(corpora)} corpora with {sum(map(len, grouped_by_corpus.indices.values()))} pieces containing cadence annotations:")
corpora
9 corpora with 258 pieces containing cadence annotations:
{'beethoven_piano_sonatas': '64 pieces',
'chopin_mazurkas': '50 pieces',
'debussy_suite_bergamasque': '4 pieces',
'dvorak_silhouettes': '12 pieces',
'grieg_lyric_pieces': '65 pieces',
'liszt_pelerinage': '19 pieces',
'medtner_tales': '19 pieces',
'schumann_kinderszenen': '13 pieces',
'tchaikovsky_seasons': '12 pieces'}
All annotation labels from the selected pieces#
all_labels = hascadence.get_facet('expanded')
print(f"{len(all_labels.index)} hand-annotated harmony labels:")
all_labels.iloc[:10, 13:].style.apply(color_background, subset="chord")
56656 hand-annotated harmony labels:
| localkey | pedal | chord | special | numeral | form | figbass | changes | relativeroot | cadence | phraseend | chord_type | globalkey_is_minor | localkey_is_minor | chord_tones | added_tones | root | bass_note | volta | pedalend | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| corpus | fname | interval | ||||||||||||||||||||
| beethoven_piano_sonatas | 01-1 | [0.0, 9.0) | i | nan | i | nan | i | nan | nan | nan | nan | nan | { | m | True | True | (0, -3, 1) | () | 0 | 0 | nan | |
| [9.0, 17.0) | i | nan | V65 | nan | V | nan | 65 | nan | nan | nan | nan | Mm7 | True | True | (5, 2, -1, 1) | () | 1 | 5 | nan | |||
| [17.0, 21.0) | i | nan | i | nan | i | nan | nan | nan | nan | nan | nan | m | True | True | (0, -3, 1) | () | 0 | 0 | nan | |||
| [21.0, 25.0) | i | nan | #viio6 | nan | #vii | o | 6 | nan | nan | nan | nan | o | True | True | (2, -1, 5) | () | 5 | 2 | nan | |||
| [25.0, 27.0) | i | nan | i6 | nan | i | nan | 6 | nan | nan | nan | nan | m | True | True | (-3, 1, 0) | () | 0 | -3 | nan | |||
| [27.0, 29.0) | i | nan | iio6 | nan | ii | o | 6 | nan | nan | nan | nan | o | True | True | (-1, -4, 2) | () | 2 | -1 | nan | |||
| [29.0, 30.0) | i | nan | V(4) | nan | V | nan | nan | 4 | nan | nan | } | M | True | True | (1, 0, 2) | () | 1 | 1 | nan | |||
| [30.0, 32.0) | i | nan | V | nan | V | nan | nan | nan | nan | HC | nan | M | True | True | (1, 5, 2) | () | 1 | 1 | nan | |||
| [32.0, 41.0) | i | nan | v | nan | v | nan | nan | nan | nan | nan | { | m | True | True | (1, -2, 2) | () | 1 | 1 | nan | |||
| [41.0, 45.0) | III | nan | IVM2 | nan | IV | M | 2 | nan | nan | nan | nan | MM7 | True | False | (4, -1, 3, 0) | () | -1 | 4 | nan |
Metadata#
dataset_metadata = hascadence.data.metadata()
hascadence_metadata = dataset_metadata.loc[hascadence.indices[()]]
hascadence_metadata.index.rename('dataset', level=0, inplace=True)
hascadence_metadata.head()
| TimeSig | KeySig | last_mc | last_mn | length_qb | last_mc_unfolded | last_mn_unfolded | length_qb_unfolded | volta_mcs | all_notes_qb | ... | typesetter | text | score integrity | comments | staff_3_ambitus | staff_3_instrument | staff_4_ambitus | staff_4_instrument | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dataset | piece | |||||||||||||||||||||
| beethoven_piano_sonatas | 01-1 | 1: 2/2 | 1: -4 | 154 | 152 | 608.0 | 308.0 | 304.0 | 1216.0 | 1476.00 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | |
| 01-2 | 1: 3/4 | 1: -1 | 62 | 61 | 183.0 | 124.0 | 122.0 | 366.0 | 526.17 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ||
| 01-3 | 1: 3/4 | 1: -4, 43: -1 | 77 | 73 | 219.0 | 196.0 | 186.0 | 558.0 | 565.50 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | ||
| 01-4 | 1: 2/2 | 1: -4 | 199 | 196 | 790.0 | 392.0 | 390.0 | 1560.0 | [[[57, 58], [59, 60, 61]]] | 2326.83 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | |
| 02-1 | 1: 2/4 | 1: 3, 127: 0, 230: 3 | 342 | 336 | 679.5 | 672.0 | 664.0 | 1336.0 | [[[115, 116, 117, 118], [119, 120, 121, 122, 1... | 1695.75 | ... | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
5 rows × 69 columns
mean_composition_years = hascadence_metadata.groupby(level=0).composed_end.mean().astype(int).sort_values()
chronological_order = mean_composition_years.index.to_list()
bar_data = pd.concat([mean_composition_years.rename('year'),
hascadence_metadata.groupby(level='dataset').size().rename('pieces')],
axis=1
).reset_index()
fig = px.bar(bar_data, x='year', y='pieces', color='dataset', title='Pieces contained in the dataset')
fig.update_traces(width=5)
Overall#
PAC: Perfect Authentic Cadence
IAC: Imperfect Authentic Cadence
HC: Half Cadence
DC: Deceptive Cadence
EC: Evaded Cadence
PC: Plagal Cadence
print(f"{all_labels.cadence.notna().sum()} cadence labels.")
value_count_df(all_labels.cadence)
3024 cadence labels.
| counts | % | |
|---|---|---|
| cadence | ||
| PAC | 1311 | 0.433532 |
| HC | 922 | 0.304894 |
| IAC | 648 | 0.214286 |
| PC | 61 | 0.020172 |
| EC | 51 | 0.016865 |
| DC | 31 | 0.010251 |
px.pie(all_labels[all_labels.cadence.notna()], names="cadence", color="cadence", color_discrete_map=CADENCE_COLORS)
Per dataset#
cadence_count_per_dataset = all_labels.groupby("corpus").cadence.value_counts()
cadence_fraction_per_dataset = cadence_count_per_dataset / cadence_count_per_dataset.groupby(level=0).sum()
px.bar(cadence_fraction_per_dataset.rename('count').reset_index(), x='corpus', y='count', color='cadence',
color_discrete_map=CADENCE_COLORS, category_orders=dict(dataset=chronological_order))
fig = px.pie(cadence_count_per_dataset.rename('count').reset_index(), names='cadence', color='cadence', values='count',
facet_col='corpus', facet_col_wrap=4, height=2000, color_discrete_map=CADENCE_COLORS)
fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))
fig.update_layout(**STD_LAYOUT)
Per phrase#
Number of cadences per phrase#
segmented = dc.PhraseSlicer().process_data(grouped_by_corpus)
phrases = segmented.get_slice_info()
phrase_segments = segmented.get_facet("expanded")
phrase_gpb = phrase_segments.groupby(level=[0,1,2])
local_keys_per_phrase = phrase_gpb.localkey.unique().map(tuple)
n_local_keys_per_phrase = local_keys_per_phrase.map(len)
phrases_with_keys = pd.concat([n_local_keys_per_phrase.rename('n_local_keys'),
local_keys_per_phrase.rename('local_keys'),
phrases], axis=1)
phrases_with_cadences = pd.concat([
phrase_gpb.cadence.nunique().rename('n_cadences'),
phrase_gpb.cadence.unique().rename('cadences').map(lambda l: tuple(e for e in l if not pd.isnull(e))),
phrases_with_keys
], axis=1)
value_count_df(phrases_with_cadences.n_cadences, counts="#phrases")
| #phrases | % | |
|---|---|---|
| n_cadences | ||
| 1 | 2839 | 0.796130 |
| 0 | 661 | 0.185362 |
| 2 | 65 | 0.018228 |
| 3 | 1 | 0.000280 |
n_cad = phrases_with_cadences.groupby(level='corpus').n_cadences.value_counts().rename('counts').reset_index().sort_values('n_cadences')
n_cad.n_cadences = n_cad.n_cadences.astype(str)
fig = px.bar(n_cad, x='corpus', y='counts', color='n_cadences', height=800, barmode='group',
labels=dict(n_cadences="#cadences in a phrase"),
category_orders=dict(dataset=chronological_order)
)
fig.show()
Combinations of cadence types for phrases with more than one cadence#
value_count_df(phrases_with_cadences[phrases_with_cadences.n_cadences > 1].cadences)
| counts | % | |
|---|---|---|
| cadences | ||
| (HC, PAC) | 24 | 0.363636 |
| (EC, PAC) | 9 | 0.136364 |
| (PAC, HC) | 6 | 0.090909 |
| (EC, HC) | 6 | 0.090909 |
| (DC, PAC) | 5 | 0.075758 |
| (IAC, PAC) | 4 | 0.060606 |
| (EC, IAC) | 3 | 0.045455 |
| (PC, PAC) | 2 | 0.030303 |
| (DC, IAC) | 1 | 0.015152 |
| (IAC, EC) | 1 | 0.015152 |
| (HC, DC) | 1 | 0.015152 |
| (DC, HC) | 1 | 0.015152 |
| (EC, DC, PAC) | 1 | 0.015152 |
| (HC, PC) | 1 | 0.015152 |
| (IAC, HC) | 1 | 0.015152 |
Positioning of cadences within phrases#
df_rows = []
y_position = 0
for ix in phrases_with_cadences[phrases_with_cadences.n_cadences > 0].sort_values('duration_qb').index:
df = phrase_segments.loc[ix]
description = str(ix)
if df.cadence.notna().any():
interval = ix[2]
df_rows.append((y_position, interval.length, "end of phrase", description))
start_pos = interval.left
cadences = df.loc[df.cadence.notna(), ['quarterbeats', 'cadence']]
cadences.quarterbeats -= start_pos
for cadence_x, cadence_type in cadences.itertuples(index=False, name=None):
df_rows.append((y_position, cadence_x, cadence_type, description))
y_position += 1
#else:
# df_rows.append((y_position, pd.NA, pd.NA, description))
data = pd.DataFrame(df_rows, columns=["phrase_ix", "x", "marker", "description"])
fig = px.scatter(data[data.x.notna()], x='x', y="phrase_ix", color="marker", hover_name="description", height=3000,
labels=dict(marker='legend'), color_discrete_map=CADENCE_COLORS)
fig.update_traces(marker_size=5)
fig.update_yaxes(autorange="reversed")
fig.show()
Cadence ultima#
phrase_segments = segmented.get_facet("expanded")
cadence_selector = phrase_segments.cadence.notna()
missing_chord_selector = phrase_segments.chord.isna()
cadence_with_missing_chord_selector = cadence_selector & missing_chord_selector
missing = phrase_segments[cadence_with_missing_chord_selector]
expanded = ms3.expand_dcml.expand_labels(phrase_segments[cadence_with_missing_chord_selector], propagate=False, chord_tones=True, skip_checks=True)
phrase_segments.loc[cadence_with_missing_chord_selector] = expanded
print(f"Ultima harmony missing for {(phrase_segments.cadence.notna() & phrase_segments.bass_note.isna()).sum()} cadence labels.")
Ultima harmony missing for 9 cadence labels.
Ultimae as Roman numeral#
def highlight(row, color="#ffffb3"):
if row.counts < 10:
return [None, None, None, None]
else:
return ["background-color: {color};"] * 4
cadence_counts = all_labels.cadence.value_counts()
ultima_root = phrase_segments.groupby(['localkey_is_minor', 'cadence']).numeral.value_counts().rename('counts').to_frame().reset_index()
ultima_root.localkey_is_minor = ultima_root.localkey_is_minor.map({False: 'in major', True: 'in minor'})
#ultima_root.style.apply(highlight, axis=1)
fig = px.pie(ultima_root, names='numeral', values='counts',
facet_row='cadence', facet_col='localkey_is_minor',
height=1500,
category_orders={'cadence': cadence_counts.index},
)
fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))
fig.update_traces(textposition='inside', textinfo='percent+label')
fig.update_layout(**STD_LAYOUT)
fig.show()
#phrase_segments.groupby(level=[0,1,2], group_keys=False).apply(lambda df: df if ((df.cadence == 'PAC') & (df.numeral == 'V')).any() else None)
Ultimae bass note as scale degree#
ultima_bass = phrase_segments.groupby(['localkey_is_minor','cadence']).bass_note.value_counts().rename('counts').reset_index()
ultima_bass.bass_note = ms3.transform(ultima_bass, ms3.fifths2sd, dict(fifths='bass_note', minor='localkey_is_minor'))
ultima_bass.localkey_is_minor = ultima_bass.localkey_is_minor.map({False: 'in major', True: 'in minor'})
#ultima_bass.style.apply(highlight, axis=1)
fig = px.pie(ultima_bass, names='bass_note', values='counts',
facet_row='cadence', facet_col='localkey_is_minor',
height=1500,
category_orders={'cadence': cadence_counts.index},
)
fig.for_each_annotation(lambda a: a.update(text=a.text.split("=")[-1]))
fig.update_traces(textposition='inside', textinfo='percent+label')
fig.update_layout(**STD_LAYOUT)
fig.show()
Chord progressions#
PACs with ultima I/i#
def remove_immediate_duplicates(l):
return tuple(a for a, b in zip(l, (None, ) + l) if a != b)
def get_progressions(selected='PAC', last_row={}, feature='chord', dataset=None, as_series=True, remove_duplicates=False):
"""Uses the nonlocal variable phrase_segments."""
last_row = {k: v if isinstance(v, tuple) else (v,) for k, v in last_row.items()}
progressions = []
for (corp, fname, *_), df in phrase_segments[phrase_segments[feature].notna()].groupby(level=[0,1,2]):
if dataset is not None and dataset not in corp:
continue
if (df.cadence == selected).fillna(False).any():
# remove chords after the last cadence label
df = df[df.cadence.fillna(method='bfill').notna()]
# group segments leading up to a cadence label
cadence_groups = df.cadence.notna().shift().fillna(False).cumsum()
for i, cadence in df.groupby(cadence_groups):
last_r = cadence.iloc[-1]
typ = last_r.cadence
if typ != selected:
continue
if any(last_r[feat] not in values for feat, values in last_row.items()):
continue
if remove_duplicates:
progressions.append(remove_immediate_duplicates(cadence[feature].to_list()))
else:
progressions.append(tuple(cadence[feature]))
if as_series:
return pd.Series(progressions, dtype='object')
return progressions
chord_progressions = get_progressions('PAC', dict(numeral=('I', 'i')), 'chord')
print(f"Progressions for {len(chord_progressions)} cadences:")
value_count_df(chord_progressions, "chord progressions")
Progressions for 1293 cadences:
| counts | % | |
|---|---|---|
| chord progressions | ||
| (V, V7, I, ii6(2), ii6, V7, I) | 12 | 0.009281 |
| (I, V7, I) | 11 | 0.008507 |
| (i, VM7, i, V7, V7(#2), V7, i) | 8 | 0.006187 |
| (I, V43, I, V6, I, V43, I, V7, I) | 6 | 0.004640 |
| (i6, i, #viio6, VI6, V6, vo6, IV6, #viio2, V(6), #viio64, i) | 6 | 0.004640 |
| ... | ... | ... |
| (V7, I6, viio6, I, ii6, I6, ii, viio, I, viio6, I6, ii6, viio7/V, V, I6, viio6, I, ii6, I6, ii, viio, I, viio6, I6, ii6, V(64), V7, I) | 1 | 0.000773 |
| (I, V43, V2, I6, I, V(64)/V, V7/V, V, V2, I6, I, V6, V, I, ii6, V, I, V43, V2, I6, I, V(64)/V, V7/V, V, V2, I6, I, V6, I, ii6, V7(9), V7, I) | 1 | 0.000773 |
| (V, V2, I6, V43, I, ii6, V(64), V7, I) | 1 | 0.000773 |
| (I, V7, I, V7, I, V7, I, V7, I, V7, I) | 1 | 0.000773 |
| (V65(b9)/ii, ii, V65(b9), I, ii6, viio7/V, V7(9), V7, I(9), I) | 1 | 0.000773 |
996 rows × 2 columns
numeral_progressions = get_progressions('PAC', dict(numeral=('I', 'i')), 'numeral')
value_count_df(numeral_progressions, "numeral progressions")
| counts | % | |
|---|---|---|
| numeral progressions | ||
| (I, V, V, I) | 15 | 0.011601 |
| (I, V, I) | 13 | 0.010054 |
| (V, V, I, ii, ii, V, I) | 12 | 0.009281 |
| (I, V, I, V, I, V, I, V, I) | 9 | 0.006961 |
| (i, V, i) | 8 | 0.006187 |
| ... | ... | ... |
| (I, I, V, I, V, V, I, V, I, IV, V, V, I) | 1 | 0.000773 |
| (I, V, I, V, I, I, V, V, V, I, V, I, V, I, ii, ii, vii, I, ii, ii, vii, I, ii, ii, V, V, I) | 1 | 0.000773 |
| (I, V, I, V, I, V, #vii, ii, V, V, I) | 1 | 0.000773 |
| (V, V, V, V, V, V, V, V, V, #vii, vi, ii, V, V, I) | 1 | 0.000773 |
| (V, ii, V, I, ii, vii, V, V, I, I) | 1 | 0.000773 |
924 rows × 2 columns
numeral_prog_no_dups = numeral_progressions.map(remove_immediate_duplicates)
value_count_df(numeral_prog_no_dups)
| counts | % | |
|---|---|---|
| (I, V, I) | 43 | 0.033256 |
| (i, V, i, V, i) | 19 | 0.014695 |
| (I, V, I, V, I) | 16 | 0.012374 |
| (I, V, I, V, I, V, I, V, I) | 13 | 0.010054 |
| (V, I, ii, V, I) | 12 | 0.009281 |
| ... | ... | ... |
| (I, V, iv, ii, V, I, V, iv, ii, V, i) | 1 | 0.000773 |
| (i, iv, bII, V, I, IV, ii, V, I) | 1 | 0.000773 |
| (I, IV, ii, V, vi, I, IV, ii, V, I) | 1 | 0.000773 |
| (I, V, IV, V, IV, iv, V, iv, V, iv, V, iv, V, i, V, bII, V, bIII, vii, V, I) | 1 | 0.000773 |
| (V, ii, V, I, ii, vii, V, I) | 1 | 0.000773 |
805 rows × 2 columns
PACs ending on scale degree 1#
Scale degrees expressed w.r.t. major scale, regardless of actual key.
bass_progressions = get_progressions('PAC', dict(bass_note=0), 'bass_note')
bass_prog = bass_progressions.map(ms3.fifths2sd)
print(f"Progressions for {len(bass_progressions)} cadences:")
value_count_df(bass_prog, "bass progressions")
Progressions for 1191 cadences:
| counts | % | |
|---|---|---|
| bass progressions | ||
| (1, 5, 1) | 20 | 0.016793 |
| (5, 5, 1, 4, 4, 5, 1) | 12 | 0.010076 |
| (1, 5, 1, 5, 5, 5, 1) | 8 | 0.006717 |
| (1, 5, 5, 1) | 8 | 0.006717 |
| (1, 4, 1, 4, 5, 5, 1) | 6 | 0.005038 |
| ... | ... | ... |
| (1, 5, 1, 5, 1, 5, 1, 5, 1, 5, 1) | 1 | 0.000840 |
| (1, 6, 4, 5, 3, 4, 5, 5, 1) | 1 | 0.000840 |
| (3, 4, 3, 7, 1, 1, 5, 4, 3, 2, 1, 7, 1, 4, 4, 3, 4, 4, 3, 4, 4, 5, 5, 1) | 1 | 0.000840 |
| (1, 2, 1, 7, 1, 1, 4, 5, 5, 1) | 1 | 0.000840 |
| (#1, 2, 7, 1, 4, #4, 5, 5, 1, 1) | 1 | 0.000840 |
846 rows × 2 columns
bass_prog_no_dups = bass_prog.map(remove_immediate_duplicates)
value_count_df(bass_prog_no_dups)
| counts | % | |
|---|---|---|
| (1, 5, 1) | 34 | 0.028547 |
| (1, 5, 1, 5, 1) | 29 | 0.024349 |
| (5, 1, 5, 1) | 16 | 0.013434 |
| (5, 1, 4, 5, 1) | 14 | 0.011755 |
| (5, 1) | 12 | 0.010076 |
| ... | ... | ... |
| (3, 4, 3, 7, 1, 5, 4, 3, 2, 1, 7, 1, 4, 3, 4, 3, 4, 5, 1) | 1 | 0.000840 |
| (1, 2, 1, 7, 1, 4, 5, 1) | 1 | 0.000840 |
| (1, 4, 1, 4, 1, 4, 1, 4, 1) | 1 | 0.000840 |
| (6, 2, 5, 1) | 1 | 0.000840 |
| (#1, 2, 7, 1, 4, #4, 5, 1) | 1 | 0.000840 |
768 rows × 2 columns
def make_sankey(data, labels, node_pos=None, margin={'l': 10, 'r': 10, 'b': 10, 't': 10}, pad=20, color='auto', **kwargs):
if color=='auto':
unique_labels = set(labels)
color_step = 100 / len(unique_labels)
unique_colors = {label: f'hsv({round(i*color_step)}%,100%,100%)' for i, label in enumerate(unique_labels)}
color = list(map(lambda l: unique_colors[l], labels))
fig = go.Figure(go.Sankey(
arrangement = 'snap',
node = dict(
pad = pad,
#thickness = 20,
#line = dict(color = "black", width = 0.5),
label = labels,
x = [node_pos[i][0] if i in node_pos else 0 for i in range(len(labels))] if node_pos is not None else None,
y = [node_pos[i][1] if i in node_pos else 0 for i in range(len(labels))] if node_pos is not None else None,
color = color,
),
link = dict(
source = data.source,
target = data.target,
value = data.value
),
),
)
fig.update_layout(margin=margin, **kwargs)
return fig
def progressions2graph_data(progressions, cut_at_stage=None):
stage_nodes = defaultdict(dict)
edge_weights = Counter()
node_counter = 0
for progression in progressions:
previous_node = None
for stage, current in enumerate(reversed(progression)):
if cut_at_stage and stage > cut_at_stage:
break
if current in stage_nodes[stage]:
current_node = stage_nodes[stage][current]
else:
stage_nodes[stage][current] = node_counter
current_node = node_counter
node_counter += 1
if previous_node is not None:
edge_weights.update([(current_node, previous_node)])
previous_node = current_node
return stage_nodes, edge_weights
def graph_data2sankey(stage_nodes, edge_weights):
data = pd.DataFrame([(u, v, w) for (u, v), w in edge_weights.items()], columns = ['source', 'target', 'value'])
node2label = {node: label for stage, nodes in stage_nodes.items() for label, node in nodes.items()}
labels = [node2label[i] for i in range(len(node2label))]
return make_sankey(data, labels)
def plot_progressions(progressions, cut_at_stage=None):
stage_nodes, edge_weights = progressions2graph_data(progressions, cut_at_stage=cut_at_stage)
return graph_data2sankey(stage_nodes, edge_weights)
Chordal roots for the 3 last stages#
plot_progressions(numeral_prog_no_dups, cut_at_stage=3)
Complete chords for the last four stages in major#
pac_major = get_progressions('PAC', dict(numeral='I', localkey_is_minor=False), 'chord')
plot_progressions(pac_major, cut_at_stage=4)
Bass degrees for the last 6 stages.#
plot_progressions(bass_prog_no_dups, cut_at_stage=7)
Bass degrees without accidentals#
def remove_sd_accidentals(t):
return tuple(map(lambda sd: sd[-1], t))
bass_prog_no_acc_no_dup = bass_prog.map(remove_sd_accidentals).map(remove_immediate_duplicates)
plot_progressions(bass_prog_no_acc_no_dup, cut_at_stage=7)
HCs ending on V#
half = get_progressions('HC', dict(numeral='V'), 'bass_note').map(ms3.fifths2sd)
print(f"Progressions for {len(half)} cadences:")
plot_progressions(half.map(remove_immediate_duplicates), cut_at_stage=5)
Progressions for 880 cadences: